# cell type annotations
display_df(cell_df_complete)

# organ annotations
display_df(organ_df_complete)

# stage annotations
display_df(stage_df_complete)

experiment_id = "SRP484717"

path_to_create_exp_script = "/Users/scarsana/Desktop/git/scRNA-Seq/scripts/Create_ExpLib_tables.py" 
path_to_barcodes_script = "/Users/scarsana/Desktop/git/scRNA-Seq/scripts/create_scRNASeq_barcode_v2.py"
experiment_type = "scRNA"
import os


path_to_output_main = "/Users/scarsana/Desktop/git/expression-annotations/Notebooks/scRNA/" 
path_to_output = "{}{}/".format(path_to_output_main, experiment_id)

path_to_initial_folder = "{}initial/".format(path_to_output)
if not os.path.exists(path_to_initial_folder):
    os.makedirs(path_to_initial_folder)

library_path_from_script = "{}scRNASeqLibrary_{}.tsv".format(path_to_initial_folder, experiment_id)
experiment_path_from_script = "{}scRNASeqExperiment_{}.tsv".format(path_to_initial_folder, experiment_id)
barcode_path = "{}scRNASeq_barcode_{}.tsv".format(path_to_initial_folder, experiment_id)


path_to_complete_folder = "{}complete/".format(path_to_output)
if not os.path.exists(path_to_complete_folder):
    os.makedirs(path_to_complete_folder)

barcode_to_add_path = "{}complete_scRNASeq_barcode_{}.tsv".format(path_to_complete_folder, experiment_id)
library_to_add_path = "{}complete_scRNASeqLibrary_{}.tsv".format(path_to_complete_folder, experiment_id)
experiment_to_add_path = "{}complete_RNASeqExperiment_{}.tsv".format(path_to_complete_folder, experiment_id)
script_file = "{}.ipynb".format(experiment_id)
commit_message_exp = '"adding annotated scRNA experiment {}"'.format(experiment_id)
commit_message_py = '"adding annotation files for {} to notebook folder"'.format(experiment_id)


## to add to git
path_to_git_annotations = "/Users/scarsana/Desktop/git/expression-annotations/scRNA_Seq/"
git_library_path = "{}scRNASeqLibrary_merged.tsv".format(path_to_git_annotations)
git_experiment_path = "{}scRNASeqExperiment.tsv".format(path_to_git_annotations)
git_barcode_path = "{}scRNASeq_barcode_{}.tsv".format(path_to_git_annotations, experiment_id)

## columns
library_cols = ['#libraryId', 'experimentId', 'platform', 'SRSId', 'anatId', 'anatName', 'cellTypeId', 'cellTypeName', 'stageId', 'stageName', 'url_GSM', 'infoOrgan', 'infoCellType_abInitio', 'infoCellType_inferred', 'clusterId', 'clusterName', 'infoStage', 'anatAnnotationStatus', 'cellTypeAnnotationStatus', 'stageAnnotationStatus', 'sex', 'strain', 'genotype', 'speciesId', 'RNAseqTags', 'protocol', 'protocolType', 'lib_name', 'sampleName', 'comment', 'condition', 'annotatorId', 'lastModificationDate']
barcode_cols = ['barcode', 'cluster', 'library', 'experiment', 'tissue', 'cell_type', 'anatId_a_posteriori', 'anatName_a_posteriori', 'anat_a_posteriori_annotationStatus', 'cellTypeId', 'cellTypeName', 'cellTypeAnnotationStatus', 'name_Library', 'comments']

## annotation sheet paths (maybe make these into their own folder)
annotation_files_path = "{}annotation_files/".format(path_to_output)

if not os.path.exists(annotation_files_path):
    os.makedirs(annotation_files_path)

info_anat_path = "{}info_anat.tsv".format(annotation_files_path)
info_anat_complete_path = "{}info_anat_complete.tsv".format(annotation_files_path)
info_stage_path = "{}info_dev_stage.tsv".format(annotation_files_path)
info_stage_complete_path = "{}info_dev_stage_complete.tsv".format(annotation_files_path)
info_celltype_path = "{}info_celltype.tsv".format(annotation_files_path)
info_celltype_complete_path = "{}info_celltype_complete.tsv".format(annotation_files_path)

## barcode file & matching library names - 10X only
path_to_barcode_file = "{}barcode_{}.tsv".format(path_to_output, experiment_id)
lib_names_path = "{}matching_lib_names_{}.tsv".format(path_to_initial_folder, experiment_id)

import warnings
warnings.simplefilter(action='ignore', category=FutureWarning)
import pandas as pd
import numpy as np
from IPython.display import display, HTML
import csv
import scanpy as sc

# displays df with the scrollbar next to the DataFrame
def display_df(df):
    pd.set_option("display.max_rows", None)
    pd.set_option("display.max_columns", None)
    display(HTML("<div style='height: 200px; overflow: auto; width: fit-content'>" +
        df.style.to_html(index=False) + "</div>"))

# function that compares two columns in a dataframe and tells you which ones are not equal (case insensitive)
def compare_columns(df, col1, col2, return_col):
    compare_return = df[col1].str.lower() != df[col2].str.lower()  
    df.loc[compare_return, return_col] 
    if not any(compare_return):
        print("The two columns are equal (case insensitive)")
    else:
        print("The following rows are not equal: ")
        print(df.loc[compare_return, [return_col, col1, col2]])

# fixes formatting of file to match libreoffice settings/historic file format
def update_format(path):
    with open(path, 'r') as file:
        filedata = file.read()
    # Replace the target string
    filedata = filedata.replace("\t\"\"", "\t")
    # Write the file out again
    with open(path, 'w') as file:
        file.write(filedata)

# checks for duplicate values in a specific column and prints those values + the corresponding library id
def dup_check(df, column):
    duplicateCheck = df.duplicated(subset=[column], keep=False)
    duplicateCheck.sort_values(inplace=True)
    if duplicateCheck.unique().any() == False:
        print("no duplicate values in " + column)
    elif duplicateCheck.unique().any() == True and column != '#libraryId':
        dups = df[duplicateCheck].loc[:,['#libraryId', column]]
        df_dups = pd.DataFrame(dups)
        df_dups.sort_values(inplace=True, by=column)
        print(df_dups)
    elif duplicateCheck.unique().any() == True and column == '#libraryId':
        print(df[duplicateCheck].loc[:,['#libraryId']])

# prints all unique values in a specific column
def unique_sorted(df, column):
    unique = df[column].unique()
    unique.sort()
    print(unique)

/var/folders/b5/crkp117d43q5mcndnwlrww3w0000gn/T/ipykernel_1635/2872653486.py:3: DeprecationWarning: 
Pyarrow will become a required dependency of pandas in the next major release of pandas (pandas 3.0),
(to allow more performant data types, such as the Arrow string type, and better interoperability with other libraries)
but was not found to be installed on your system.
If this would cause problems for you,
please provide us feedback at https://github.com/pandas-dev/pandas/issues/54466
        
  import pandas as pd

! python3 $path_to_create_exp_script $experiment_id $path_to_initial_folder $experiment_type

/Users/scarsana/Desktop/git/scRNA-Seq/scripts/Create_ExpLib_tables.py:97: SyntaxWarning: invalid escape sequence '\('
  all_protoc = [w.replace('(', '\(') for w in all_protoc]
/Users/scarsana/Desktop/git/scRNA-Seq/scripts/Create_ExpLib_tables.py:98: SyntaxWarning: invalid escape sequence '\)'
  all_protoc = [w.replace(')', '\)') for w in all_protoc] 
/Users/scarsana/Desktop/git/scRNA-Seq/scripts/Create_ExpLib_tables.py:11: DeprecationWarning: 
Pyarrow will become a required dependency of pandas in the next major release of pandas (pandas 3.0),
(to allow more performant data types, such as the Arrow string type, and better interoperability with other libraries)
but was not found to be installed on your system.
If this would cause problems for you,
please provide us feedback at https://github.com/pandas-dev/pandas/issues/54466
        
  import pandas as pd
Be patient, it may take a few minutes.
0it [00:00, ?it/s]
0 samples dont have attributes, try to find them somewhere else
0it [00:00, ?it/s]
0 samples dont have attributes

supp_1 = pd.read_csv("supp_1.csv", index_col=False, keep_default_na=False, na_values=['NULL','null', 'nan','NaN', " "], dtype=object)

library_1 = pd.read_csv(library_path_from_script, sep='\t', index_col=False, keep_default_na=False, na_values=['NULL','null', 'nan','NaN', " "], dtype=object)

library_1[['lib_name_2', 'lib_name_3']] = library_1['lib_name'].str.split(" ", n=1, expand = True)

combined = library_1.merge(supp_1, how = 'outer',left_on='lib_name_2', right_on='cell')

low_quality =  combined[combined['cell'].isna()]
new_library =  combined[~combined['cell'].isna()]

low_quality_remove = low_quality[["#libraryId", "experimentId"]]

low_quality_remove["comments"] = "not passed QC from authors, see https://doi.org/10.1101/2024.02.05.578945"

/var/folders/b5/crkp117d43q5mcndnwlrww3w0000gn/T/ipykernel_56532/159512783.py:1: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  low_quality_remove["comments"] = "not passed QC from authors, see https://doi.org/10.1101/2024.02.05.578945"

low_quality_remove["annotatorId"] = "SAC" 
low_quality_remove["date"] = "2025-02-18"

/var/folders/b5/crkp117d43q5mcndnwlrww3w0000gn/T/ipykernel_56532/1504161933.py:1: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  low_quality_remove["annotatorId"] = "SAC"
/var/folders/b5/crkp117d43q5mcndnwlrww3w0000gn/T/ipykernel_56532/1504161933.py:2: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  low_quality_remove["date"] = "2025-02-18"

low_quality_remove.to_csv("complete/to_remove_libraries.tsv", sep="\t", index=False, quoting=csv.QUOTE_ALL)

new_library[["EML", "big_EML", "stage", "infoStage_2", "devTime"]].drop_duplicates().sort_values( by = "devTime")

new_library['stageTime'] = new_library[['infoStage_2', 'devTime']].apply(': '.join, axis=1)

/var/folders/b5/crkp117d43q5mcndnwlrww3w0000gn/T/ipykernel_56532/3278253462.py:1: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  new_library['stageTime'] = new_library[['infoStage_2', 'devTime']].apply(': '.join, axis=1)

new_library[["EML", "big_EML", "stage"]].drop_duplicates().sort_values( by = "big_EML")

new_library['cell_type_all'] = new_library[['big_EML', 'EML']].apply(': '.join, axis=1)

/var/folders/b5/crkp117d43q5mcndnwlrww3w0000gn/T/ipykernel_56532/2404253388.py:1: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  new_library['cell_type_all'] = new_library[['big_EML', 'EML']].apply(': '.join, axis=1)

new_library['infoOrgan'] = new_library['stageTime'].values
new_library['infoStage'] = new_library['stageTime'].values
new_library['infoCellType_abInitio'] = new_library['cell_type_all'].values

/var/folders/b5/crkp117d43q5mcndnwlrww3w0000gn/T/ipykernel_56532/2109825958.py:1: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  new_library['infoOrgan'] = new_library['stageTime'].values
/var/folders/b5/crkp117d43q5mcndnwlrww3w0000gn/T/ipykernel_56532/2109825958.py:2: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  new_library['infoStage'] = new_library['stageTime'].values
/var/folders/b5/crkp117d43q5mcndnwlrww3w0000gn/T/ipykernel_56532/2109825958.py:3: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  new_library['infoCellType_abInitio'] = new_library['cell_type_all'].values

library = new_library[library_cols]
display_df(library)
library.to_csv(library_to_add_path, sep="\t", index=False, quoting=csv.QUOTE_ALL)

library = pd.read_csv(library_to_add_path, sep='\t', index_col=False, keep_default_na=False, na_values=['NULL','null', 'nan','NaN', " "], dtype=object)
display_df(library)

infoOrgan = library['infoOrgan'].drop_duplicates().sort_values()
organ_df = pd.DataFrame(infoOrgan)
organ_df = organ_df.reindex(columns=[*organ_df.columns.tolist(), 'notes_anat', 'anatId_', 'anatName_', 'anatAnnotationStatus_', 'infoOrgan_new', 'comment_anat'], fill_value="")
organ_df.to_csv(info_anat_path, sep="\t", index=False, quoting=csv.QUOTE_ALL)
if not os.path.exists(info_anat_complete_path): 
    organ_df.to_csv(info_anat_complete_path, sep="\t", index=False, quoting=csv.QUOTE_ALL)

# options for anatAnnotationStatus: perfect match, missing child term, other

organ_df_complete = pd.read_csv(info_anat_complete_path, sep='\t', index_col=False, keep_default_na=False, na_values=['NULL','null', 'nan','NaN', " "], dtype=object)
display_df(organ_df_complete)

library = library.merge(organ_df_complete, left_on='infoOrgan', right_on='infoOrgan')

library['anatId'] = library['anatId_'].values
library['anatName'] = library['anatName_'].values
library['anatAnnotationStatus'] = library['anatAnnotationStatus_'].values

## optional - update infoOrgan, add anat-specific comments 
#library['infoOrgan'] = library['infoOrgan_new'].values
#library['comment'] = library[['comment', 'comment_anat']].agg(' '.join, axis=1)

# reformat, save progress
library = library[library_cols]
display_df(library)
library.to_csv(library_to_add_path, sep="\t", index=False, quoting=csv.QUOTE_ALL)

infoStage = library['infoStage'].drop_duplicates().sort_values()
stage_df = pd.DataFrame(infoStage)
stage_df = stage_df.reindex(columns=[*stage_df.columns.tolist(), 'notes_stage', 'stageId_', 'stageName_', 'stageAnnotationStatus_', 'infoStage_new','comment_stage'], fill_value="")
stage_df.to_csv(info_stage_path, sep="\t", index=False, quoting=csv.QUOTE_ALL)
if not os.path.exists(info_stage_complete_path): 
    stage_df.to_csv(info_stage_complete_path, sep="\t", index=False, quoting=csv.QUOTE_ALL)

# options for stageAnnotationStatus: perfect match, missing child term, other

stage_df_complete = pd.read_csv(info_stage_complete_path, sep='\t', index_col=False, keep_default_na=False, na_values=['NULL','null', 'nan','NaN', " "], dtype=object)
display_df(stage_df_complete)

library = library.merge(stage_df_complete, left_on='infoStage', right_on='infoStage')

library['stageId'] = library['stageId_'].values
library['stageName'] = library['stageName_'].values
library['stageAnnotationStatus'] = library['stageAnnotationStatus_'].values

## optional - update infoOrgan, add anat-specific comments 
#library['infoStage'] = library['infoStage_new'].values
#library['comment'] = library[['comment', 'comment_stage']].agg(' '.join, axis=1)

# reformat, save progress
library = library[library_cols]
display_df(library)
library.to_csv(library_to_add_path, sep="\t", index=False, quoting=csv.QUOTE_ALL)

cell_type = library['infoCellType_abInitio'].drop_duplicates().sort_values()
cell_df = pd.DataFrame(cell_type)
cell_df = cell_df.reindex(columns=[*cell_df.columns.tolist(), 'notes_cell', 'cellTypeId_', 'cellTypeName_', 'cellTypeAnnotationStatus_', 'cell_type_new','comment_cell'], fill_value="")
cell_df.to_csv(info_celltype_path, sep="\t", index=False)
if not os.path.exists(info_celltype_complete_path): 
    cell_df.to_csv(info_celltype_complete_path, sep="\t", index=False)

cell_df_complete = pd.read_csv(info_celltype_complete_path, sep='\t', index_col=False, keep_default_na=False, na_values=['NULL','null', 'nan','NaN', " "], dtype=object)
display_df(cell_df_complete)

library = library.merge(cell_df_complete, left_on='infoCellType_abInitio', right_on='infoCellType_abInitio')

library['cellTypeId'] = library['cellTypeId_'].values
library['cellTypeName'] = library['cellTypeName_'].values
library['cellTypeAnnotationStatus'] = library['cellTypeAnnotationStatus_'].values

## optional - update infoOrgan, add anat-specific comments 
#library['infoCellType_inferred'] = library['cell_type_new'].values
#library['comment'] = library[['comment', 'comment_cell']].agg(' '.join, axis=1)

# reformat, save progress
library = library[library_cols]
display_df(library)
library.to_csv(library_to_add_path, sep="\t", index=False, quoting=csv.QUOTE_ALL)

library.loc[:, "sex"] = "NA"
#library.loc[library["sex"] == "female", "sex"] = "F"

library.loc[:,'strain'] = 'Hartley'

#library.loc[:,'genotype'] = ''

#library.loc[:,'speciesId'] = ''

# view
display_df(library)

# making these variables because we use them again in the experiment file
# usually 10X Genomics V1/V2/V3/V3.1, Smart-seq, Smart-seq2
#my_protocol = ''
# Full-length or 3'end or 5'end
#my_protocolType = ""

#library.loc[:,'protocol'] = my_protocol
#library.loc[:,'protocolType'] = my_protocolType
# scRNA-seq, Sn-scRNA-seq
library.loc[:,'RNAseqTags'] = 'scRNA-seq'

# view
display_df(library)

# ex. control, diet, light, reproductive capacity, time post mortem, time post feeding, 
# exercise details, menstruation, personality, litter size 
#library.loc[library["condition"] == "old", "condition"] = "new"

# view
display_df(library)

library.loc[:,'annotatorId'] = 'SAC'
library.loc[:,'lastModificationDate'] = '2025-02-20'

# view
display_df(library)

library.loc[:,'comment'] = 'no PMID but DOI: 10.1101/2024.02.05.578945,  all info found in supplementary table 1 or taken directly from the paper'

library_file_complete = library[library_cols]

library_file_complete.to_csv(library_to_add_path, sep="\t", index=False, quoting=csv.QUOTE_ALL)

# view
display_df(library_file_complete)

experiment = pd.read_csv(experiment_path_from_script, sep='\t', index_col=False, keep_default_na=False, na_values=['NULL','null', 'nan','NaN', " "], dtype=object)
experiment.head()

library_to_add = pd.read_csv(library_to_add_path, sep='\t', index_col=False, keep_default_na=False, na_values=['NULL','null', 'nan','NaN', " "], dtype=object)

# this will give you the number of rows in the complete library file 
# this should be the number of annotated libraries
ann_lib = len(library_to_add.index)
len(library_to_add.index)

541

# partial or total
experiment.loc[:,'experimentStatus'] = 'partial'
# scRNA-seq, Sn-scRNA-seq for both we put: 'Sn-scRNA-seq, scRNA-seq'
experiment.loc[:,'RNAseqTags'] = 'scRNA-seq'


# see above cell, also can add as free text
experiment.loc[:,'numberOfAnnotatedLibraries'] = ann_lib

# these variables should already exist from above but if not can just add as free text
#experiment.loc[:,'protocol'] = my_protocol
#experiment.loc[:,'protocolType'] = my_protocolType

experiment.head()

experiment.loc[:,'GSE'] = 'GSE253670'
#experiment.loc[:,'Bioproject'] = '' 
#experiment.loc[:,'PMID'] = ''
experiment.loc[:,'reference_url'] = 'https://www.biorxiv.org/content/10.1101/2024.02.05.578945v1.full'
experiment.loc[:,'DOI'] = '10.1101/2024.02.05.578945'
#experiment.loc[:,'xrefs'] = ''

experiment.head()

experiment.loc[:,'comment'] = 'no PMID because paper is still in preprint although PMID 37284942 methods paper may also reference this dataset however we were unable to access this paper, partial because i removed cells that did not pass QC'

experiment.head()

experiment.to_csv(experiment_to_add_path, sep="\t", index=False, quoting=csv.QUOTE_ALL)

library_to_add = pd.read_csv(library_to_add_path, sep='\t', index_col=False, keep_default_na=False, na_values=['NULL','null', 'nan','NaN', " "], dtype=object)
experiment_to_add = pd.read_csv(experiment_to_add_path, sep='\t', index_col=False, keep_default_na=False, na_values=['NULL','null', 'nan','NaN', " "], dtype=object)

# pull from git and pull in library/experiment file
! git pull
git_library = pd.read_csv(git_library_path, sep='\t', index_col=False, keep_default_na=False, na_values=['NULL','null', 'nan','NaN', " "], dtype=object)
git_experiment = pd.read_csv(git_experiment_path, sep='\t', index_col=False, keep_default_na=False, na_values=['NULL','null', 'nan','NaN', " "], dtype=object)

# library file
if set(library_to_add.columns) == set(git_library.columns):
    print('The columns in the library file match')
else:
    print('The columns in the library file DO NOT MATCH')

# experiment file
if set(experiment_to_add.columns) == set(git_experiment.columns):
    print('The columns in the experiment file match')
else:
    print('The columns in the experiment file DO NOT MATCH')


# maybe to make this something more like "COLUMNS GOOD - LIBRARY" and "COLUMNS BAD - EXPERIMENT"

Already up to date.
The columns in the library file match
The columns in the experiment file match

library_git_plus_new = pd.concat([git_library, library_to_add], ignore_index = True, sort = False)
old_length = git_library.shape[0]
start = old_length - 2
end = old_length + 5
view_lib = library_git_plus_new.iloc[start:end]
view_lib

experiment_git_plus_new = pd.concat([git_experiment, experiment_to_add], ignore_index = True, sort = False)
experiment_git_plus_new.tail(n=3)

! git pull

Already up to date.

library_git_plus_new.to_csv(git_library_path, sep="\t", index=False, quoting=csv.QUOTE_ALL)
update_format(git_library_path)
experiment_git_plus_new.to_csv(git_experiment_path, sep="\t", index=False, quoting=csv.QUOTE_ALL)
update_format(git_experiment_path)

! git status

On branch develop
Your branch is up to date with 'origin/develop'.

Changes not staged for commit:
  (use "git add <file>..." to update what will be committed)
  (use "git restore <file>..." to discard changes in working directory)
	modified:   ../../../scRNA_Seq/scRNASeqExperiment.tsv
	modified:   ../../../scRNA_Seq/scRNASeqLibrary_merged.tsv

Untracked files:
  (use "git add <file>..." to include in what will be committed)
	./
	../SRP537812_waiting/

no changes added to commit (use "git add" and/or "git commit -a")

# smart-seq (no barcode file)
! git add $git_experiment_path $git_library_path

! git status

On branch develop
Your branch is up to date with 'origin/develop'.

Changes to be committed:
  (use "git restore --staged <file>..." to unstage)
	modified:   ../../../scRNA_Seq/scRNASeqExperiment.tsv
	modified:   ../../../scRNA_Seq/scRNASeqLibrary_merged.tsv

Untracked files:
  (use "git add <file>..." to include in what will be committed)
	./
	../SRP537812_waiting/

! git commit -m $commit_message_exp

[develop 059ebde] adding annotated scRNA experiment SRP484717
 2 files changed, 542 insertions(+)

! git push

Enumerating objects: 9, done.
Counting objects: 100% (9/9), done.
Delta compression using up to 12 threads
Compressing objects: 100% (5/5), done.
Writing objects: 100% (5/5), 15.34 KiB | 86.00 KiB/s, done.
Total 5 (delta 4), reused 0 (delta 0), pack-reused 0
remote: 
remote: To create a merge request for develop, visit:
remote:   https://gitlab.sib.swiss/Bgee/expression-annotations/-/merge_requests/new?merge_request%5Bsource_branch%5D=develop
remote: 
To https://gitlab.sib.swiss/Bgee/expression-annotations.git
   ef16fe4..059ebde  develop -> develop

! git status

! git add $path_to_output

! git commit -m $commit_message_py

! git push

	infoCellType_abInitio	notes_cell	cellTypeId_	cellTypeName_	cellTypeAnnotationStatus_
0	ICM: EPI	inner cell mass: epiblast	CL:0000352	epiblast cell	perfect match
1	ICM: ICM	icm: inner cell mass	CL:2000020	inner cell mass cell	perfect match
2	ICM: PE	icm: primitive endoderm	CL:0000223	endodermal cell	other
3	Prelineage: 8 cell		CL:0000353	blastoderm cell	other
4	Prelineage: Morula		CL:0000353	blastoderm cell	other
5	Prelineage: Precavitation		CL:0000353	blastoderm cell	other
6	TE: mural	TE = trophoectoderm, per paper mural TE initiates attachment and implantation, no subterms for TE cells in CL	CL:1000274	trophectodermal cell	missing child term
7	TE: polar	TE = trophoectoderm, no subterms for TE cells in CL	CL:1000274	trophectodermal cell	missing child term

	infoOrgan	notes_anat	anatId_	anatName_	anatAnnotationStatus_
0	16 cell: E4		UBERON:0000085	morula	missing child term
1	16 cell: E4.5		UBERON:0000085	morula	missing child term
2	16-32 cell: E4.5	seems morula is appropriate for 16-64 cell stages	UBERON:0000085	morula	missing child term
3	16-32 cell: E4.75	seems morula is appropriate for 16-64 cell stages	UBERON:0000085	morula	missing child term
4	8 cell: E3.5		UBERON:0019252	8-cell stage embryo	perfect match
5	Early blastocyst: E4.5		UBERON:0000358	blastocyst	missing child term
6	Early blastocyst: E5		UBERON:0000358	blastocyst	missing child term
7	Early blastocyst: E5.25		UBERON:0000358	blastocyst	missing child term
8	Late blastocyst: E5.5		UBERON:0000358	blastocyst	missing child term
9	Late blastocyst: E5.75		UBERON:0000358	blastocyst	missing child term
10	Late blastocyst: E6		UBERON:0000358	blastocyst	missing child term
11	Middle blastocyst: E5.25		UBERON:0000358	blastocyst	missing child term
12	Middle blastocyst: E5.5		UBERON:0000358	blastocyst	missing child term
13	Middle blastocyst: E5.75		UBERON:0000358	blastocyst	missing child term

	infoStage	stageId_	stageName_	stageAnnotationStatus_
0	16 cell: E4	UBERON:0000107	cleavage stage	missing child term
1	16 cell: E4.5	UBERON:0000107	cleavage stage	missing child term
2	16-32 cell: E4.5	UBERON:0000107	cleavage stage	missing child term
3	16-32 cell: E4.75	UBERON:0000107	cleavage stage	missing child term
4	8 cell: E3.5	UBERON:0007236	8 cell stage	perfect match
5	Early blastocyst: E4.5	UBERON:0000108	blastula stage	missing child term
6	Early blastocyst: E5	UBERON:0000108	blastula stage	missing child term
7	Early blastocyst: E5.25	UBERON:0000108	blastula stage	missing child term
8	Late blastocyst: E5.5	UBERON:0000108	blastula stage	missing child term
9	Late blastocyst: E5.75	UBERON:0000108	blastula stage	missing child term
10	Late blastocyst: E6	UBERON:0000108	blastula stage	missing child term
11	Middle blastocyst: E5.25	UBERON:0000108	blastula stage	missing child term
12	Middle blastocyst: E5.5	UBERON:0000108	blastula stage	missing child term
13	Middle blastocyst: E5.75	UBERON:0000108	blastula stage	missing child term

	EML	big_EML	stage	infoStage_2	devTime
0	8 cell	Prelineage	8C	8 cell	E3.5
1	Morula	Prelineage	16C	16 cell	E4
413	Precavitation	Prelineage	16C	16 cell	E4.5
11	Morula	Prelineage	16C	16 cell	E4.5
300	ICM	ICM	EB	Early blastocyst	E4.5
297	PE	ICM	EB	Early blastocyst	E4.5
275	polar	TE	EB	Early blastocyst	E4.5
274	EPI	ICM	EB	Early blastocyst	E4.5
61	Precavitation	Prelineage	16-32 cell	16-32 cell	E4.5
79	Morula	Prelineage	16-32 cell	16-32 cell	E4.5
89	ICM	ICM	16-32 cell	16-32 cell	E4.5
119	polar	TE	16-32 cell	16-32 cell	E4.5
257	Morula	Prelineage	16-32 cell	16-32 cell	E4.75
256	Precavitation	Prelineage	16-32 cell	16-32 cell	E4.75
577	polar	TE	EB	Early blastocyst	E5
579	ICM	ICM	EB	Early blastocyst	E5
583	EPI	ICM	EB	Early blastocyst	E5
501	PE	ICM	MB	Middle blastocyst	E5.25
499	polar	TE	MB	Middle blastocyst	E5.25
16	PE	ICM	EB	Early blastocyst	E5.25
18	polar	TE	EB	Early blastocyst	E5.25
19	ICM	ICM	EB	Early blastocyst	E5.25
20	EPI	ICM	EB	Early blastocyst	E5.25
149	polar	TE	MB	Middle blastocyst	E5.5
114	PE	ICM	LB	Late blastocyst	E5.5
104	mural	TE	LB	Late blastocyst	E5.5
162	EPI	ICM	MB	Middle blastocyst	E5.5
150	PE	ICM	MB	Middle blastocyst	E5.5
154	mural	TE	MB	Middle blastocyst	E5.5
239	mural	TE	LB	Late blastocyst	E5.75
147	polar	TE	LB	Late blastocyst	E5.75
7	polar	TE	MB	Middle blastocyst	E5.75
448	PE	ICM	MB	Middle blastocyst	E5.75
146	EPI	ICM	LB	Late blastocyst	E5.75
2	EPI	ICM	MB	Middle blastocyst	E5.75
236	PE	ICM	LB	Late blastocyst	E5.75
224	polar	TE	LB	Late blastocyst	E6
223	EPI	ICM	LB	Late blastocyst	E6
221	mural	TE	LB	Late blastocyst	E6
213	PE	ICM	LB	Late blastocyst	E6

	EML	big_EML	stage
150	PE	ICM	MB
2	EPI	ICM	MB
146	EPI	ICM	LB
16	PE	ICM	EB
114	PE	ICM	LB
19	ICM	ICM	EB
20	EPI	ICM	EB
89	ICM	ICM	16-32 cell
0	8 cell	Prelineage	8C
79	Morula	Prelineage	16-32 cell
61	Precavitation	Prelineage	16-32 cell
1	Morula	Prelineage	16C
413	Precavitation	Prelineage	16C
104	mural	TE	LB
18	polar	TE	EB
119	polar	TE	16-32 cell
7	polar	TE	MB
147	polar	TE	LB
154	mural	TE	MB

SRP484717 / GSE253670¶

annotation summary¶

set variables, import packages, define functions¶

script¶

remove low quality cells¶

collect IDs from low quality cells to remove¶

modify library file to include information from supplementary table 1¶

library annnotations¶

anatomical entity¶

stage¶

cell type - smart-seq¶

sex, strain, genotype, speciesId¶

protocol & RNAseqTags¶

condition¶

annotator id, last modification date¶

comments¶

save complete file with correct columns¶

experiment annotations¶

experiment and protocol details¶

paper and xrefs¶

comments¶

save complete file¶

QA time¶

to add things here¶

check columns match¶

view files¶

add annotations to git¶

add annotation folder and script to git¶

	#libraryId	experimentId	platform	SRSId	anatId	anatName	cellTypeId	cellTypeName	stageId	stageName	url_GSM	infoOrgan	infoCellType_abInitio	infoStage	anatAnnotationStatus	cellTypeAnnotationStatus	stageAnnotationStatus	sex	strain	speciesId	RNAseqTags	protocol	protocolType	lib_name	sampleName	comment	annotatorId	lastModificationDate
59080	ERX11130831	ERP136630	Illumina NovaSeq 6000	ERS16039576	UBERON:0006538	respiratory system fluid/secretion			EcabDv:0000004	mature stage		bronchoalveolar lavage fluid		over 5 years	perfect match		perfect match	M	Swiss Warmblood	9796	scRNA-seq	10X Genomics V3.1	3'end	51C	SAMEA114056345		SAC	2025-02-12
59081	ERX11130830	ERP136630	Illumina NovaSeq 6000	ERS16039575	UBERON:0006538	respiratory system fluid/secretion			EcabDv:0000004	mature stage		bronchoalveolar lavage fluid		over 5 years	perfect match		perfect match	F	Swiss Warmblood	9796	scRNA-seq	10X Genomics V3.1	3'end	46C	SAMEA114056344		SAC	2025-02-12
59082	SRX23310999	SRP484717	Illumina NovaSeq 6000	SRS20187327	UBERON:0019252	8-cell stage embryo	CL:0000353	blastoderm cell	UBERON:0007236	8 cell stage	https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi...	8 cell: E3.5	Prelineage: 8 cell	8 cell: E3.5	perfect match	other	perfect match	NA	Hartley	10141	scRNA-seq	Smart-Seq2	Full-length	JC_1_1 (21PG50-2)	SAMN39504047	no PMID but DOI: 10.1101/2024.02.05.578945, a...	SAC	2025-02-20
59083	SRX23311255	SRP484717	Illumina NovaSeq 6000	SRS20187583	UBERON:0000085	morula	CL:0000353	blastoderm cell	UBERON:0000107	cleavage stage	https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi...	16 cell: E4	Prelineage: Morula	16 cell: E4	missing child term	other	missing child term	NA	Hartley	10141	scRNA-seq	Smart-Seq2	Full-length	JC_1_10 (21PG39-1)	SAMN39504046	no PMID but DOI: 10.1101/2024.02.05.578945, a...	SAC	2025-02-20
59084	SRX23311256	SRP484717	Illumina NovaSeq 6000	SRS20187584	UBERON:0000358	blastocyst	CL:0000352	epiblast cell	UBERON:0000108	blastula stage	https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi...	Middle blastocyst: E5.75	ICM: EPI	Middle blastocyst: E5.75	missing child term	perfect match	missing child term	NA	Hartley	10141	scRNA-seq	Smart-Seq2	Full-length	JC_1_100 (21PG55-2)	SAMN39504045	no PMID but DOI: 10.1101/2024.02.05.578945, a...	SAC	2025-02-20
59085	SRX23311257	SRP484717	Illumina NovaSeq 6000	SRS20187585	UBERON:0000358	blastocyst	CL:0000352	epiblast cell	UBERON:0000108	blastula stage	https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi...	Middle blastocyst: E5.75	ICM: EPI	Middle blastocyst: E5.75	missing child term	perfect match	missing child term	NA	Hartley	10141	scRNA-seq	Smart-Seq2	Full-length	JC_1_101 (21PG55-2)	SAMN39504044	no PMID but DOI: 10.1101/2024.02.05.578945, a...	SAC	2025-02-20
59086	SRX23311258	SRP484717	Illumina NovaSeq 6000	SRS20187586	UBERON:0000358	blastocyst	CL:0000352	epiblast cell	UBERON:0000108	blastula stage	https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi...	Middle blastocyst: E5.75	ICM: EPI	Middle blastocyst: E5.75	missing child term	perfect match	missing child term	NA	Hartley	10141	scRNA-seq	Smart-Seq2	Full-length	JC_1_102 (21PG55-2)	SAMN39504043	no PMID but DOI: 10.1101/2024.02.05.578945, a...	SAC	2025-02-20

	#experimentId	experimentName	experimentDescription	experimentSource	experimentStatus	RNAseqTags	numberOfAnnotatedLibraries	protocol	protocolType	GSE	Bioproject	PMID	reference_url	DOI	xrefs	comment
109	SRP487479	Transcriptomic response in osteoarthritis dete...	We used single-cell RNA sequencing to characte...	SRA	partial	scRNA-seq	4	10X Genomics V3.1	3'end	GSE254840	PRJNA1072060	39507442	https://atm.amegroups.org/article/view/129887/...	10.21037/atm-24-40		partial b/c removed samples with osteoarthritis
110	ERP136630	This is a repository for all raw data of singl...	The transcriptomic profile and the composition...	ENA	partial	scRNA-seq	5	10X Genomics V3.1	3'end		PRJEB51962	38153159	https://onlinelibrary.wiley.com/doi/10.1111/im...	10.1111/imm.13745	36292607[PMID], 36105804[PMID]	removed asthmatic samples and one pacbio isose...
111	SRP484717	The Guinea Pig Serves as an Alternative Model ...	Preimplantation development is a pivotal phase...	SRA	partial	scRNA-seq	541	Smart-Seq2	Full-length	GSE253670	PRJNA1066746		https://www.biorxiv.org/content/10.1101/2024.0...	10.1101/2024.02.05.578945		no PMID because paper is still in preprint alt...